Inspired by biological findings, we present a system that is able to robustly identify a large number of pre-trained objects in realtime. In contrast to related work, we do not res...
Stephan Hasler, Heiko Wersing, Stephan Kirstein, E...
In this paper a novel complex classifier architecture is proposed. The architecture has a hierarchical tree-like structure with simple artificial neural networks (ANNs) at each no...
In this paper, we propose a hierarchical classifier structure for gender classification based on facial images by reducing the complexity of the original problem. In the proposed f...
Atypical observations, which are called outliers, are one of difficulties to apply standard Gaussian density based pattern classification methods. Large number of outliers makes di...
This paper proposes an efficient three-stage classifier for handwritten digit recognition based on NN (Neural Network) and SVM (Support Vector Machine) classifiers. The classifica...